© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31076
    Prev
    Next
    INDEX
    Explanations

    is it like that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪijåĴĮ
    -0.10
    çijŁ
    -0.10
    éĥ½ä¸įæķ¢
    -0.09
    ackle
    -0.09
    æĪijä¼ļ
    -0.09
    æĪijçŁ¥éģĵ
    -0.09
     конеÑĩно
    -0.09
    åľ¨æĪijçļĦ
    -0.09
    _coeffs
    -0.09
    硬
    -0.09
    POSITIVE LOGITS
    æŁIJç§į
    0.11
    伪
    0.10
    ï¼Ł↵
    0.10
    æŁIJç§įç¨ĭ度
    0.10
    ä¸ĢåĽŀäºĭ
    0.09
    纵
    0.09
    æĥĩ
    0.09
    éĤ£éº¼
    0.09
    izard
    0.09
    æ£Ģ
    0.09
    Activations Density 0.038%

    No Known Activations